Liam had spent the entire train ride agonizing. He’d seen the announcement on the publication’s Twitter feed: a glowing endorsement, the author’s name splashed across the banner. Not his. He wanted to shout, but he couldn’t seem to find his voice.

He adjusted his glasses, repeatedly wiping the nonexistent dust from the lenses. His hands wouldn’t stop fidgeting. The strap of his messenger bag felt heavy and restrictive against his shoulder. A nervous sweat beaded on his forehead.

He thought about the meeting he now had to go to. He knew everyone would have seen the article. They would probably congratulate *her*, the supposed author, and he would have to sit there. He'd have to pretend. He tightened his jaw and stared at the passing scenery, trying to control the rapid thrum in his chest.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238